Towards agricultural autonomy: crop row detection under varying field conditions using deep learning

TL;DR

The deep learning model was found to be robust against shadows and growth stages of the crop while the performance was reduced under direct sunlight, increasing weed density, tramlines and discontinuities in crop rows when evaluated with the novel metric.

Abstract

This paper presents a novel metric to evaluate the robustness of deep learning based semantic segmentation approaches for crop row detection under different field conditions encountered by a field robot. A dataset with ten main categories encountered under various field conditions was used for testing. The effect on these conditions on the angular accuracy of crop row detection was compared. A deep convolutional encoder decoder network is implemented to predict crop row masks using RGB input images. The predicted mask is then sent to a post processing algorithm to extract the crop rows. The deep learning model was found to be robust against shadows and growth stages of the crop while the performance was reduced under direct sunlight, increasing weed density, tramlines and discontinuities in crop rows when evaluated with the novel metric.

Figures (13)

• Figure 1: Improvement of prediction at 5, 10, 20 and 40 epochs respectively (Left to Right)
• Figure 2: IoU Visualization of the U-Net Prediction
• Figure 3: Line angle error calculation
• Figure 4: Sample image and respective ground truth label mask
• Figure 5: Husky Robot with Realsense Cameras